Structure of attractors in randomly connected networks

Abstract

The deterministic dynamics of randomly connected neural networks are studied, where a state of binary neurons evolves according to a discreet-time synchronous update rule. We give a theoretical support that the overlap of systems' states between the current and a previous time develops in time according to a Markovian stochastic process in large networks. This Markovian process predicts how often a network revisits one of previously visited states, depending on the system size. The state concentration probability, i.e., the probability that two distinct states co-evolve to the same state, is utilized to analytically derive various characteristics that quantify attractors' structure. The analytical predictions about the total number of attractors, the typical cycle length, and the number of states belonging to all attractive cycles match well with numerical simulations for relatively large system sizes.

arXiv comment13 pages, 7 figures, to be published by Phys Rev E

References in corpus (7)

• Complexity without chaos: Plasticity within random recurrent networks generates robust timing and motor control
• Stimulus-Dependent Suppression of Chaos in Recurrent Neural Networks
• Transition to chaos in random networks with cell-type-specific connectivity
• Transition from regular to complex behaviour in a discrete deterministic asymmetric neural network model
• Attractors in fully asymmetric neural networks
• Dynamics of asymmetric kinetic Ising systems revisited
• State Concentration Exponent as a Measure of Quickness in Kauffman-type Networks

Cited by in corpus (4)

• Effect of dilution in asymmetric recurrent neural networks
• On the number of limit cycles in diluted neural networks
• Space of Functions Computed by Deep-Layered Machines
• Predict or classify: The deceptive role of time-locking in brain signal classification